
#import library
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import numpy as np # linear algebra
import matplotlib.pyplot as plt
import seaborn as sns  # visualization tool
from datetime import datetime
# plotly
import plotly 
plotly.offline.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import warnings
#sns.set(font_scale=1.5)
warnings.filterwarnings("ignore")


# loading csv File
ps_df=pd.read_csv(r"E:\0001Almabetter\2.numerical python programming\project-eda-numeric-python\Play Store Data.csv")


# Display the Play Store App data head

ps_df.head()


ps_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10841 entries, 0 to 10840
Data columns (total 13 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   App             10841 non-null  object 
 1   Category        10841 non-null  object 
 2   Rating          9367 non-null   float64
 3   Reviews         10841 non-null  object 
 4   Size            10841 non-null  object 
 5   Installs        10841 non-null  object 
 6   Type            10840 non-null  object 
 7   Price           10841 non-null  object 
 8   Content Rating  10840 non-null  object 
 9   Genres          10841 non-null  object 
 10  Last Updated    10841 non-null  object 
 11  Current Ver     10833 non-null  object 
 12  Android Ver     10838 non-null  object 
dtypes: float64(1), object(12)
memory usage: 1.1+ MB


# Finding the number of rows and columns in the given dataset
print(ps_df.columns)

Index(['App', 'Category', 'Rating', 'Reviews', 'Size', 'Installs', 'Type',
       'Price', 'Content Rating', 'Genres', 'Last Updated', 'Current Ver',
       'Android Ver'],
      dtype='object')


ps_df.shape

(10841, 13)


ps_df.dtypes

App                object
Category           object
Rating            float64
Reviews            object
Size               object
Installs           object
Type               object
Price              object
Content Rating     object
Genres             object
Last Updated       object
Current Ver        object
Android Ver        object
dtype: object


ps_df.describe()


# This user define function will give the type,count of null and non null values as well as null ratio
def playstoreinfo():
    temp=pd.DataFrame(index=ps_df.columns)
    temp["datatype"]=ps_df.dtypes
    temp["not null values"]=ps_df.count()
    temp["null value"]=ps_df.isnull().sum()
    temp["% of the null value"]=ps_df.isnull().mean()
    temp["unique count"]=ps_df.nunique()
    return temp
playstoreinfo()


# The rows containing NaN values in the Android Ver column
ps_df[ps_df["Android Ver"].isnull()]


# Finding the different values the 'Android Ver' column takes
ps_df["Android Ver"].value_counts()

4.1 and up            2451
4.0.3 and up          1501
4.0 and up            1375
Varies with device    1362
4.4 and up             980
2.3 and up             652
5.0 and up             601
4.2 and up             394
2.3.3 and up           281
2.2 and up             244
4.3 and up             243
3.0 and up             241
2.1 and up             134
1.6 and up             116
6.0 and up              60
7.0 and up              42
3.2 and up              36
2.0 and up              32
5.1 and up              24
1.5 and up              20
4.4W and up             12
3.1 and up              10
2.0.1 and up             7
8.0 and up               6
7.1 and up               3
4.0.3 - 7.1.1            2
5.0 - 8.0                2
1.0 and up               2
7.0 - 7.1.1              1
4.1 - 7.1.1              1
5.0 - 6.0                1
2.2 - 7.1.1              1
5.0 - 7.1.1              1
Name: Android Ver, dtype: int64


ps_df.shape

(10841, 13)


# dropping rows corresponding to the to the NaN values in the 'Android Ver' column.
ps_df =ps_df[ps_df['Android Ver'].notna()]
# Shape of the updated dataframe
ps_df.shape

(10838, 13)


# The rows containing NaN values in the Current Ver column
ps_df[ps_df["Current Ver"].isnull()]


# Finding the different values the 'Current Ver' column takes
ps_df['Current Ver'].value_counts()

Varies with device    1459
1.0                    809
1.1                    263
1.2                    178
2.0                    151
                      ... 
5.44.1                   1
7.16.8                   1
04.08.00                 1
2.10.06                  1
2.0.148.0                1
Name: Current Ver, Length: 2831, dtype: int64


# dropping rows corresponding to the values which contain NaN in the column 'Current Ver'.
ps_df=ps_df[ps_df["Current Ver"].notna()]
# Shape of the updated dataframe
ps_df.shape

(10830, 13)


# The row containing NaN values in the Type column
ps_df[ps_df["Type"].isnull()]


# Finding the different values the 'Type' column takes
ps_df["Type"].value_counts()

Free    10032
Paid      797
Name: Type, dtype: int64


# Replacing the NaN value in 'Type' column corresponding to row index 9148 with 'Free'
ps_df.loc[9148,'Type']='Free'


ps_df[ps_df['Type'].isnull()]


# The rows containing NaN values in the Rating column
ps_df[ps_df['Rating'].isnull()]


ps_df['Rating'].max()

5.0


ps_df[(ps_df['Rating'] <1) | (ps_df['Rating']>5)]


ps_df['Rating'].mean()

4.191837606837612


ps_df['Rating'].median()

4.3


ps_df


fig, ax = plt.subplots(2,1, figsize=(12,7))
sns.distplot(ps_df['Rating'],color='firebrick',ax=ax[0]);
sns.boxplot(x='Rating',data=ps_df, ax=ax[1]);


ps_df['Rating'].median()

4.3


# Replacing the NaN values in the 'Rating' colunm with its median value
ps_df['Rating'].fillna(value=ps_df['Rating'].median(),inplace=True)


ps_df['Rating'].value_counts()

4.3    2546
4.4    1108
4.5    1037
4.2     951
4.6     823
4.1     707
4.0     567
4.7     499
3.9     386
3.8     303
5.0     274
3.7     239
4.8     234
3.6     174
3.5     163
3.4     128
3.3     102
4.9      87
3.0      83
3.1      69
3.2      63
2.9      45
2.8      42
2.7      25
2.6      25
2.5      21
2.3      20
2.4      19
1.0      16
2.2      14
1.9      13
2.0      12
1.7       8
1.8       8
2.1       8
1.6       4
1.4       3
1.5       3
1.2       1
Name: Rating, dtype: int64


ps_df['Rating'].isna().sum()

0


# Handling the error values in the Play store data
ps_df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 10830 entries, 0 to 10840
Data columns (total 13 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   App             10830 non-null  object 
 1   Category        10830 non-null  object 
 2   Rating          10830 non-null  float64
 3   Reviews         10830 non-null  object 
 4   Size            10830 non-null  object 
 5   Installs        10830 non-null  object 
 6   Type            10830 non-null  object 
 7   Price           10830 non-null  object 
 8   Content Rating  10830 non-null  object 
 9   Genres          10830 non-null  object 
 10  Last Updated    10830 non-null  object 
 11  Current Ver     10830 non-null  object 
 12  Android Ver     10830 non-null  object 
dtypes: float64(1), object(12)
memory usage: 1.4+ MB


ps_df['App'].value_counts()

ROBLOX                                                9
CBS Sports App - Scores, News, Stats & Watch Live     8
Candy Crush Saga                                      7
8 Ball Pool                                           7
ESPN                                                  7
                                                     ..
Meet U - Get Friends for Snapchat, Kik & Instagram    1
U-Report                                              1
U of I Community Credit Union                         1
Waiting For U Launcher Theme                          1
iHoroscope - 2018 Daily Horoscope & Astrology         1
Name: App, Length: 9649, dtype: int64


# Inspecting the duplicates values.
ps_df[ps_df['App']=='ROBLOX']


ps_df[ps_df['App'].duplicated()]


# dropping duplicates from the 'App' column.
ps_df.drop_duplicates(subset = 'App', inplace = True)
ps_df.shape

(9649, 13)


# Checking whether the duplicates in the 'App' column are taken care of or not
ps_df[ps_df['App']=='ROBLOX']


ps_df[ps_df['App'].duplicated()]


ps_df['Last Updated']

0         January 7, 2018
1        January 15, 2018
2          August 1, 2018
3            June 8, 2018
4           June 20, 2018
               ...       
10836       July 25, 2017
10837        July 6, 2018
10838    January 20, 2017
10839    January 19, 2015
10840       July 25, 2018
Name: Last Updated, Length: 9649, dtype: object


# Pandas to_datetime() function applied to the values in the last updated column helps to convert string Date time into Python Date time object.
ps_df["Last Updated"] = pd.to_datetime(ps_df['Last Updated'])
ps_df.head()


ps_df['Last Updated']

0       2018-01-07
1       2018-01-15
2       2018-08-01
3       2018-06-08
4       2018-06-20
           ...    
10836   2017-07-25
10837   2018-07-06
10838   2017-01-20
10839   2015-01-19
10840   2018-07-25
Name: Last Updated, Length: 9649, dtype: datetime64[ns]


ps_df['Price'].value_counts()

0          8896
$0.99       143
$2.99       124
$1.99        73
$4.99        70
           ... 
$18.99        1
$389.99       1
$19.90        1
$1.75         1
$1.04         1
Name: Price, Length: 92, dtype: int64


s = '$1.23'


if "$" in s:
    print(s[1:])

1.23


# Creating a function drop-dollar which dropps the $ symbol if it is present and returns the output which is of float datatype.
def convert_dollar(val):
    if '$' in val:
        return float(val[1:])
    else:
        return float(val)


# The drop_dollar funtion applied to the price column
ps_df['Price'] = ps_df['Price'].apply(lambda x: convert_dollar(x))


ps_df['Price'].max()

400.0


ps_df['Price'].dtype

dtype('float64')


ps_df[ps_df['Price']==0]


ps_df[ps_df['Price']!=0]


s1 = "1,000,00+"

s1

'1,000,00+'


s1 = s1.replace(",","")

s1

'100000+'


s1[ 0: -1]

'100000'


# Checking the contents of the 'Installs' column
ps_df['Installs'].value_counts()

1,000,000+        1416
100,000+          1112
10,000+           1029
10,000,000+        937
1,000+             886
100+               709
5,000,000+         607
500,000+           504
50,000+            468
5,000+             467
10+                384
500+               328
50+                204
50,000,000+        202
100,000,000+       188
5+                  82
1+                  67
500,000,000+        24
1,000,000,000+      20
0+                  14
0                    1
Name: Installs, dtype: int64


# Creating a function convert_plus which drops the '+' symbol if it is present and returns the output which is of integer datatype.

def convert_plus(val):
    if '+' and ',' in val:
        new = int(val[:-1].replace(',',''))
        return new
    elif '+' in val:
        new1 = int(val[:-1])
        return new1
    else:
        return int(val)


# The drop_plus funtion applied to the main dataframe

ps_df['Installs'] = ps_df['Installs'].apply(lambda x: convert_plus(x))
ps_df.head()


ps_df['Installs']

0           10000
1          500000
2         5000000
3        50000000
4          100000
           ...   
10836        5000
10837         100
10838        1000
10839        1000
10840    10000000
Name: Installs, Length: 9649, dtype: int64


ps_df['Installs'].dtype

dtype('int64')


ps_df['Size'].value_counts()

Varies with device    1227
12M                    181
11M                    181
13M                    177
14M                    176
                      ... 
721k                     1
430k                     1
429k                     1
200k                     1
619k                     1
Name: Size, Length: 457, dtype: int64


# Defining a function to convert all the entries in KB to MB and then converting them to float datatype.

def convert_kb_to_mb(val):
    try:
        if 'M' in val:
            return float(val[:-1])
        elif 'k' in val:
            return round(float(val[:-1])/1024, 4)
        else:
            return val
    except:
        return val


# The kb_to_mb funtion applied to the size column

ps_df['Size'] = ps_df['Size'].apply(lambda x: convert_kb_to_mb(x))
ps_df.head()


ps_df['Size'].dtype

dtype('O')


ps_df['Size'] = ps_df['Size'].apply(lambda x: str(x).replace('Varies with device', 'NaN') if 'Varies with device' in str(x) else x)


ps_df['Size'].value_counts()

NaN       1227
12.0       181
11.0       181
13.0       177
14.0       176
          ... 
0.7041       1
0.4199       1
0.4189       1
0.1953       1
0.6045       1
Name: Size, Length: 456, dtype: int64


ps_df['Size'] = ps_df['Size'].apply(lambda x: float(x))


ps_df['Size'].dtype

dtype('float64')


ps_df['Size'].mean(), ps_df['Size'].median()

(20.413555699358753, 12.0)


ps_df['Size'].max()

100.0


 ps_df[ps_df['Size'] != 'Varies with device']['Size'].max()

100.0


round(ps_df['Size'].mean(),4)

20.4136


# Finding max, min, mean, and median in the Size column excluding the 'Varies with device' values.

max_size = ps_df['Size'].max()

min_size = ps_df['Size'].min()

mean_size = round(ps_df['Size'].mean(),4)

median_size = ps_df['Size'].median()

[max_size, min_size, mean_size, median_size]

[100.0, 0.0083, 20.4136, 12.0]


ps_df[['Size']].boxplot()

<AxesSubplot:>


# Distplot
fig, ax = plt.subplots(2,1, figsize=(12,7))
sns.distplot(ps_df[ps_df['Size'] != 'Varies with device']['Size'], color='purple', ax=ax[0])
sns.boxplot(x='Size',data=ps_df, ax=ax[1])

<AxesSubplot:xlabel='Size'>


ps_df['Size'].fillna(ps_df['Size'].median(),inplace=True)


# Converting the datatype of the values in the reviews column from string to int
ps_df['Reviews'] = ps_df['Reviews'].astype(int)
ps_df.head()


ps_df.describe()


Rating = ps_df['Rating']
Size = ps_df['Size']
Installs = ps_df['Installs']
Reviews = ps_df['Reviews']
Type = ps_df['Type']
Price = ps_df['Price']

p = sns.pairplot(pd.DataFrame(list(zip(Rating, Size, np.log(Installs), np.log10(Reviews), Price, Type)), 
                        columns=['Rating','Size', 'Installs', 'Reviews', 'Price','Type']), hue='Type')
p.fig.suptitle("Pairwise Plot - Rating, Size, Installs, Reviews, Price",x=0.5, y=1.0, fontsize=16)

Text(0.5, 1.0, 'Pairwise Plot - Rating, Size, Installs, Reviews, Price')


def plot_number_category(data):
    sns.set(style="whitegrid")  # Set the style to whitegrid
    fig, ax = plt.subplots()
    fig.set_size_inches(15, 7)
    ax.set_facecolor('yellow')  # Set background color to yellow
    sns.countplot(data['Category'], ax=ax, palette='pastel')  # Using Seaborn's pastel color palette
    plt.xticks(rotation=90)
    
    # Add count values on top of each bar
    for p in ax.patches:
        ax.annotate(format(p.get_height(), '.0f'), 
                    (p.get_x() + p.get_width() / 2., p.get_height()), 
                    ha='center', va='center', 
                    xytext=(0, 5), 
                    textcoords='offset points')
    
    plt.show()

# Assuming 'playstore_data' is your DataFrame containing the data
plot_number_category(ps_df)


sns.set_style("whitegrid", {'axes.grid' : False})
sns.lmplot(y='Rating',x='Size',data=ps_df,col="Category", hue="Category",col_wrap=4,line_kws={'color': 'red'})

<seaborn.axisgrid.FacetGrid at 0x2eb46571a90>


# Get the top 5 categories based on the number of installations
top5_cat = ps_df.groupby('Category')['Installs'].sum().nlargest(5).index.tolist()

# Filter the data for the top 5 categories
data_top5 = ps_df.groupby('Category')['Installs'].sum().loc[top5_cat].reset_index(name='Number_Installations')

# Plotting
plt.figure(figsize=(12, 6));  # Increase figure width
plt.title('Comparing top 5 categories based on Installs', color='white');  # Set title color to white
bar_plot = sns.barplot(y=data_top5['Category'], x=data_top5['Number_Installations'], palette='viridis');

# Annotate each bar with its corresponding value
for index, value in enumerate(data_top5['Number_Installations']):
    plt.text(value, index, f'{value:,}', va='center', fontsize=12, color='white')  # Set text color to white

plt.xlabel('Number of Installations', color='white');  # Set xlabel color to white
plt.ylabel('Category', color='white');  # Set ylabel color to white
plt.gca().set_facecolor('red');  # Set background color to red
plt.grid(axis='x', linestyle='--', alpha=0.7);  # Add gridlines on x-axis

# Adjust x-axis limits to ensure all numbers are visible
plt.xlim(right=data_top5['Number_Installations'].max() * 1.1);  # Extend the limit by 10% on the right side
plt.show(bar_plot);


# Grouping by Content Rating and calculating total installations
data_cont = ps_df.groupby('Content Rating')['Installs'].sum().reset_index(name='Number_Installations');

# Plotting
plt.figure(figsize=(10, 5));
plt.title('Total Installations by Content Rating', color='white');  # Set title color to white
bar_plot = sns.barplot(x=data_cont['Content Rating'], y=data_cont['Number_Installations'], palette='viridis');

# Annotate each bar with its corresponding value
for index, value in enumerate(data_cont['Number_Installations']):
    plt.text(index, value, f'{value:,}', ha='center', fontsize=12, color='red');  # Set text color to red

plt.xlabel('Content Rating', color='white');  # Set xlabel color to white
plt.ylabel('Number of Installations', color='white');  # Set ylabel color to white
plt.gca().set_facecolor('yellow');  # Set background color to black
plt.grid(axis='y', linestyle='--', alpha=0.7);  # Add gridlines on y-axis

plt.show(bar_plot);


ps_df.groupby('Content Rating')['Installs'].sum()

Content Rating
Adults only 18+        2000000
Everyone           52177775851
Everyone 10+        4016271795
Mature 17+          2437986878
Teen               16487275393
Unrated                  50500
Name: Installs, dtype: int64


# Get the top 5 apps based on the number of installations
top_app = ps_df.groupby('App').size().reset_index(name='Count').nlargest(5, 'Count');
top5_app = top_app['App'].tolist();

# Filter the data for the top 5 apps
data_app = ps_df.groupby('App')['Installs'].sum().loc[top5_app].reset_index(name='Number_Installations');

# Plotting
plt.figure(figsize=(10, 5));
plt.title('Top 5 Apps by Installations', color='blue');  # Set title color to blue
bar_plot = sns.barplot(x=data_app['Number_Installations'], y=data_app['App'], palette='YlGnBu');  # Set palette to Yellow-Green-Blue

# Annotate each bar with its corresponding value
for index, value in enumerate(data_app['Number_Installations']):
    plt.text(value, index, f'{value:,}', va='center', fontsize=12, color='black');  # Set text color to black

plt.xlabel('Number of Installations', color='blue');  # Set xlabel color to blue
plt.ylabel('App', color='blue');  # Set ylabel color to blue
plt.gca().set_facecolor('yellow');  # Set background color to yellow
plt.grid(axis='x', linestyle='--', alpha=0.7);  # Add gridlines on x-axis

plt.show(bar_plot);


# Reading the userreviews.csv file
ur_df=pd.read_csv(r"E:\0001Almabetter\2.numerical python programming\project-eda-numeric-python\User Reviews.csv")


# Checking the top 10 rows of the data

ur_df.head()


ur_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 64295 entries, 0 to 64294
Data columns (total 5 columns):
 #   Column                  Non-Null Count  Dtype  
---  ------                  --------------  -----  
 0   App                     64295 non-null  object 
 1   Translated_Review       37427 non-null  object 
 2   Sentiment               37432 non-null  object 
 3   Sentiment_Polarity      37432 non-null  float64
 4   Sentiment_Subjectivity  37432 non-null  float64
dtypes: float64(2), object(3)
memory usage: 2.5+ MB


# Checking shape and column in dataframe
print(ur_df.columns)
rows=ur_df.shape[0]
columns=ur_df.shape[1]
print(f"the no of rows is {rows} and no of columns is {columns}")

Index(['App', 'Translated_Review', 'Sentiment', 'Sentiment_Polarity',
       'Sentiment_Subjectivity'],
      dtype='object')
the no of rows is 64295 and no of columns is 5


def Urinfo():
    temp1=pd.DataFrame(index=ur_df.columns)
    temp1["datatype"]=ur_df.dtypes
    temp1["not null values"]=ur_df.count()
    temp1["null value"]=ur_df.isnull().sum()
    temp1["% of the null value"]=ur_df.isnull().mean().round(4)*100
    temp1["unique count"]=ur_df.nunique()
    return temp1
Urinfo()


# Finding the total no of NaN values in each column.
ur_df.isnull().sum()

App                           0
Translated_Review         26868
Sentiment                 26863
Sentiment_Polarity        26863
Sentiment_Subjectivity    26863
dtype: int64


# checking the NaN values in the translated rview column
ur_df[ur_df['Translated_Review'].isnull()]


# The rows corresponding to the NaN values in the translated_review column, where the rest of the columns are non null.
ur_df[ur_df['Translated_Review'].isnull() & ur_df['Sentiment'].notna()]


# Deleting the rows containing NaN values
ur_df = ur_df.dropna()


# The shape of the updated df
ur_df.shape

(37427, 5)


ur_df.iloc[1:22]


# Inspecting the sentiment column
ur_df['Sentiment'].value_counts()

Positive    23998
Negative     8271
Neutral      5158
Name: Sentiment, dtype: int64


# Finding correlation between different columns in the play store data
ps_df.corr()


# Heat map for play_store
plt.figure(figsize = (20,10))
sns.heatmap(ps_df.corr(), annot= True)
plt.title('Corelation Heatmap for Playstore Data', size=20)

Text(0.5, 1.0, 'Corelation Heatmap for Playstore Data')


merged_df = pd.merge(ps_df, ur_df, on='App', how = "inner")


merged_df.shape

(35929, 17)


def merged_dfinfo():
    temp = pd.DataFrame(index=merged_df.columns)
    temp['data_type'] = merged_df.dtypes
    temp["count of non null values"] = merged_df.count()
    temp['NaN values'] = merged_df.isnull().sum()
    temp['% NaN values'] =merged_df.isnull().mean()
    temp['unique_count'] = merged_df.nunique() 
    return temp
merged_dfinfo()


merged_df.corr()


# Correlation heatmap
# Heat Map for the merged data frame
plt.figure(figsize = (15,10))
sns.heatmap(merged_df.corr(), annot= True, cmap='Greens')
plt.title(' Heatmap for merged Dataframe', size=20)

Text(0.5, 1.0, ' Heatmap for merged Dataframe')


merged_df = merged_df.dropna(subset=['Sentiment', 'Translated_Review'])


merged_df.shape

(35929, 17)


merged_df.isna().sum()

App                       0
Category                  0
Rating                    0
Reviews                   0
Size                      0
Installs                  0
Type                      0
Price                     0
Content Rating            0
Genres                    0
Last Updated              0
Current Ver               0
Android Ver               0
Translated_Review         0
Sentiment                 0
Sentiment_Polarity        0
Sentiment_Subjectivity    0
dtype: int64


data = ps_df['Type'].value_counts() 
labels = ['Free', 'Paid']

# create pie chart
plt.figure(figsize=(10,10))
colors = ["#00EE76","#7B8895"]
explode=(0.01,0.1)
plt.pie(data, labels = labels, colors = colors, autopct='%.2f%%',explode=explode,textprops={'fontsize': 15})
plt.title('Distribution of Paid and Free apps',size=15,loc='center')
plt.legend()

<matplotlib.legend.Legend at 0x2eb4cbc5fd0>


ps_df['Content Rating'].unique()

array(['Everyone', 'Teen', 'Everyone 10+', 'Mature 17+',
       'Adults only 18+', 'Unrated'], dtype=object)


# Content rating of the apps
data = ps_df['Content Rating'].value_counts()
labels = ['Everyone', 'Teen', 'Everyone 10+', 'Mature 17+','Adults only 18+', 'Unrated']

#create pie chart
plt.figure(figsize=(10,10))
explode=(0,0.1,0.1,0.1,0.0,1.3)
colors = ['C4', 'r', 'c', 'g', 'm', 'k']
plt.pie(data, labels = labels, colors = colors, autopct='%.2f%%',explode=explode,textprops={'fontsize': 15})
plt.title('Content Rating',size=20,loc='center')
plt.legend()

<matplotlib.legend.Legend at 0x2eb4c744580>


ps_df.groupby("Category")["App"].count().sort_values(ascending= False)

Category
FAMILY                 1829
GAME                    959
TOOLS                   825
BUSINESS                420
MEDICAL                 395
PERSONALIZATION         374
PRODUCTIVITY            374
LIFESTYLE               369
FINANCE                 345
SPORTS                  325
COMMUNICATION           315
HEALTH_AND_FITNESS      288
PHOTOGRAPHY             281
NEWS_AND_MAGAZINES      254
SOCIAL                  239
BOOKS_AND_REFERENCE     221
TRAVEL_AND_LOCAL        219
SHOPPING                202
DATING                  171
VIDEO_PLAYERS           163
MAPS_AND_NAVIGATION     131
EDUCATION               119
FOOD_AND_DRINK          112
ENTERTAINMENT           102
AUTO_AND_VEHICLES        85
LIBRARIES_AND_DEMO       83
WEATHER                  79
HOUSE_AND_HOME           74
EVENTS                   64
ART_AND_DESIGN           63
PARENTING                60
COMICS                   56
BEAUTY                   53
Name: App, dtype: int64


x = ps_df['Category'].value_counts()
y = ps_df['Category'].value_counts().index
x_list = []
y_list = []
for i in range(len(x)):
    x_list.append(x[i])
    y_list.append(y[i])


#Number of apps belonging to each category in the playstore
plt.figure(figsize=(20,10))
plt.xlabel('Number of Apps', size=15)
plt.ylabel('App Categories', size=15)
graph = sns.barplot(y = x_list, x = y_list, palette= "tab10")
graph.set_title("Top categories on Playstore", fontsize = 25)
graph.set_xticklabels(graph.get_xticklabels(), rotation= 45, horizontalalignment='right',);


# Percentage of apps belonging to each category in the playstore
plt.figure(figsize=(18,18))
plt.pie(ps_df.Category.value_counts(), labels=ps_df.Category.value_counts().index, autopct='%1.2f%%')
my_circle = plt.Circle( (0,0), 0.50, color='white')
p=plt.gcf()
p.gca().add_artist(my_circle)
plt.title('% of apps share in each Category', fontsize = 25)
plt.show()


# total app installs in each category of the play store

a = ps_df.groupby(['Category'])['Installs'].sum().sort_values()
a.plot.barh(figsize=(15,10), color = 'c', )
plt.ylabel('Total app Installs', fontsize = 15)
plt.xlabel('App Categories', fontsize = 15)
plt.xticks()
plt.title('Total app installs in each category', fontsize = 20)

Text(0.5, 1.0, 'Total app installs in each category')


# Average app ratings

ps_df['Rating'].value_counts().plot.bar(figsize=(20,8), color = 'm' )
plt.xlabel('Average rating',fontsize = 15 )
plt.ylabel('Number of apps', fontsize = 15)
plt.title('Average rating of apps in Playstore', fontsize = 20)
plt.legend()

<matplotlib.legend.Legend at 0x2eb4cd86e20>


# Defining a function grouped_rating to group the ratings as mentioned above
def Rating_app(val):
  ''''
  This function help to categories the rating from 1 to 5
  as Top_rated,Above_average,Average & below Average
  '''
  if val>=4:
    return 'Top rated'
  elif val>3 and val<4:
    return 'Above Average'
  elif val>2 and val<3:
    return 'Average'
  else:
    return 'Below Average'


# Applying grouped_rating function
ps_df['Rating_group']=ps_df['Rating'].apply(lambda x: Rating_app(x))


# Average app ratings 
ps_df['Rating_group'].value_counts().plot.bar(figsize=(15,5), color = 'royalblue')
plt.xlabel('Rating Group', fontsize = 12)
plt.ylabel('Number of apps', fontsize = 12)
plt.title('Average app ratings', fontsize = 18)
plt.xticks(rotation=0)
plt.legend()

<matplotlib.legend.Legend at 0x2eb4e8a9a00>


def findtop10incategory(str):
    str = str.upper()
    top10 = ps_df[ps_df['Category'] == str]
    top10apps = top10.sort_values(by='Installs', ascending=False).head(10)
    plt.figure(figsize=(15,6), dpi=100)
    plt.title('Top 10 Installed Apps',size = 20)  
    graph = sns.barplot(x = top10apps.App, y = top10apps.Installs, palette= "icefire")
    graph.set_xticklabels(graph.get_xticklabels(), rotation= 45, horizontalalignment='right')


findtop10incategory('GAME')


 # Creating a df for only free apps
 
 free_df = ps_df[ps_df['Type'] == 'Free']


# Creating a df for top free apps

top_free_df = free_df[free_df['Installs'] == free_df['Installs'].max()]
top10free_apps=top_free_df.nlargest(10, 'Installs', keep='first')
top10free_apps.head(10)


# Top free apps

top_free_df['App']

152                            Google Play Books
335     Messenger – Text and Video Chat for Free
336                           WhatsApp Messenger
338                 Google Chrome: Fast & Secure
340                                        Gmail
341                                     Hangouts
391                Skype - free IM & video calls
865                            Google Play Games
1654                              Subway Surfers
2544                                    Facebook
2545                                   Instagram
2554                                     Google+
2808                               Google Photos
3117                   Maps - Navigate & Explore
3127                          Google Street View
3234                                      Google
3454                                Google Drive
3665                                     YouTube
3687                     Google Play Movies & TV
3736                                 Google News
Name: App, dtype: object


# Categories in which the top 20 free apps belong to
top_free_df['Category'].value_counts().plot.bar(figsize=(20,6), color= ('darkcyan','blueviolet'))
plt.xlabel('Category', size=15)
plt.ylabel('Number of apps', size=15)
plt.title('Categories in which the top 20 free apps belong', size=19)
plt.xticks(rotation=45)
plt.legend()

<matplotlib.legend.Legend at 0x2eb4f27c5e0>


# Creating a df containing only paid apps
paid_df=ps_df[ps_df['Type']=='Paid']


# Number of apps that can be installed at a particular price 

paid_df.groupby('Price')['App'].count().sort_values(ascending= False).plot.bar(figsize = (20,6), color = 'crimson')

<AxesSubplot:xlabel='Price'>


# Creatng a new column 'Revenue' in paid_df
paid_df['Revenue'] = paid_df['Installs']*paid_df['Price']
paid_df.head()


# Top app in the paid category

paid_df[paid_df['Revenue'] == paid_df['Revenue'].max()]


# Top 10 paid apps in the play store
top10paid_apps=paid_df.nlargest(10, 'Revenue', keep='first')
top10paid_apps['App']

2241                        Minecraft
5351                        I am rich
5356                I Am Rich Premium
4034                    Hitman Sniper
7417    Grand Theft Auto: San Andreas
2883              Facetune - For Free
5578          Sleep as Android Unlock
8804              DraStic DS Emulator
4367         I'm Rich - Trump Edition
4362                       💎 I'm rich
Name: App, dtype: object


# Categories in which the top 10 paid apps belong to
top10paid_apps['Category'].value_counts().plot.bar(figsize=(15,5), color= ["orange", "red", "green", "blue", "purple"])
plt.xlabel('Category',size=12)
plt.ylabel('Number of apps',size=12)
plt.title('Categories in which the top 10 paid apps belong', size=15)
plt.xticks(rotation=0)
plt.legend()

<matplotlib.legend.Legend at 0x2eb4f4c0970>


# Top paid apps according to the revenue generated through installs alone
top10paid_apps.groupby('App')['Revenue'].mean().sort_values(ascending= True).plot.barh(figsize=(16,10), color='darkorange')
plt.xlabel('Revenue Generated (USD)', size=15)
plt.title('Top apps based on revenue generated through installation fee', size=20)
plt.legend()

<matplotlib.legend.Legend at 0x2eb4f4c0640>


# Paid apps with the highest number of installs
paid_df[paid_df['Revenue'] == paid_df['Revenue'].max()]


# Values calculated earlier
[mean_size,median_size,max_size,min_size]

[20.4136, 12.0, 100.0, 0.0083]


# Function to group the apps based on its size in MB

def size_apps(var):
  '''
  This function groups the size of an app 
  between ~0 to 100 MB into certain intervals.
  '''
  try:
    if var < 1:
      return 'Below 1'
    elif var >= 1 and var <10:
      return '1-10'
    elif var >= 10 and var <20:
      return '10-20'
    elif var >= 20 and var <30:
      return '20-30'
    elif var >= 30 and var <40:
      return '30-40'
    elif var >= 40 and var <50:
      return '40-50'
    elif var >= 50 and var <60:
      return '50-60'
    elif var >= 60 and var <70:
      return '60-70'
    elif var >= 70 and var <80:
      return '70-80'
    elif var >= 80 and var <90:
      return '80-90'
    else:
      return '90 and above'
  except:
    return var


ps_df['size_group']=ps_df['Size'].apply(lambda x : size_apps(x))
ps_df.head()


# no of apps belonging to each size group
ps_df['size_group'].value_counts().plot.barh(figsize=(20,8),color='r').invert_yaxis()
plt.title("Number of apps in different size groups", size=20)
plt.ylabel('App size in MB', size=15)
plt.xlabel('No of apps', size=15)
plt.legend()

<matplotlib.legend.Legend at 0x2eb4f57bb20>


# average no of user reviews in each size group
ps_df.groupby('size_group')['Reviews'].mean().sort_values().plot.barh(figsize=(20,8), color = 'green')
plt.title("Average number of user reviews (in millions)", size=20)
plt.xlabel('Average no of user reviews', size=15)
plt.ylabel('App size in MB', size=15)
plt.legend()

<matplotlib.legend.Legend at 0x2eb4f5dcf40>


# average number of app installs in each category

ps_df.groupby('size_group')['Installs'].mean().sort_values(ascending= False).plot.barh(figsize=(20,8),color='sandybrown').invert_yaxis()
plt.title("Average number of app installs (In 10 millions)", size=20)
plt.ylabel('App size in MB', size=15)
plt.xlabel('Average no of app installs',  size=15)
plt.legend()

<matplotlib.legend.Legend at 0x2eb4f61e340>


ps_df['Android Ver'].replace(to_replace=['4.4W and up','Varies with device'], value=['4.4','1.0'],inplace=True)
ps_df['Android Ver'].replace({k: '1.0' for k in ['1.0','1.0 and up','1.5 and up','1.6 and up']},inplace=True)
ps_df['Android Ver'].replace({k: '2.0' for k in ['2.0 and up','2.0.1 and up','2.1 and up','2.2 and up','2.2 - 7.1.1','2.3 and up','2.3.3 and up']},inplace=True)
ps_df['Android Ver'].replace({k: '3.0' for k in ['3.0 and up','3.1 and up','3.2 and up']},inplace=True)
ps_df['Android Ver'].replace({k: '4.0' for k in ['4.0 and up','4.0.3 and up','4.0.3 - 7.1.1','4.1 and up','4.1 - 7.1.1','4.2 and up','4.3 and up','4.4','4.4 and up']},inplace=True)
ps_df['Android Ver'].replace({k: '5.0' for k in ['5.0 - 6.0','5.0 - 7.1.1','5.0 - 8.0','5.0 and up','5.1 and up']},inplace=True)
ps_df['Android Ver'].replace({k: '6.0' for k in ['6.0 and up']},inplace=True)
ps_df['Android Ver'].replace({k: '7.0' for k in ['7.0 - 7.1.1','7.0 and up','7.1 and up']},inplace=True)
ps_df['Android Ver'].replace({k: '8.0' for k in ['8.0 and up']},inplace=True)
ps_df['Android Ver'].fillna('1.0', inplace=True)


print(ps_df.groupby('Category')['Android Ver'].value_counts())
Type_cat = ps_df.groupby('Category')['Android Ver'].value_counts().unstack().plot.bar(figsize=(25,8), width=2)
plt.xticks()
plt.show()

Category        Android Ver
ART_AND_DESIGN  4.0            50
                2.0             9
                3.0             2
                1.0             1
                5.0             1
                               ..
WEATHER         4.0            38
                1.0            23
                2.0            10
                5.0             7
                3.0             1
Name: Android Ver, Length: 199, dtype: int64


# Basic inspection
ur_df.columns

Index(['App', 'Translated_Review', 'Sentiment', 'Sentiment_Polarity',
       'Sentiment_Subjectivity'],
      dtype='object')


import matplotlib
counts = list(ur_df['Sentiment'].value_counts())
labels = 'Positive Reviews', 'Negative Reviews','Neutral Reviews'
matplotlib.rcParams['font.size'] = 20
matplotlib.rcParams['figure.figsize'] = (10, 15)
plt.pie(counts, labels=labels, explode=[0.01, 0.05, 0.05], shadow=True, autopct="%.2f%%")
plt.title('Percentage of Review Sentiments', fontsize=20)
plt.axis('off')
plt.legend(bbox_to_anchor=(0.9, 0, 0.5, 1))
plt.show()


# positive reviews
positive_ur_df=ur_df[ur_df['Sentiment']=='Positive']
positive_ur_df


positive_ur_df.groupby('App')['Sentiment'].value_counts().nlargest(10).plot.barh(figsize=(10,8),color='seagreen').invert_yaxis()
plt.title("Top 10 positive review apps")
plt.xlabel('Total number of positive reviews')
plt.legend()

<matplotlib.legend.Legend at 0x2eb50c13730>


negative_ur_df=ur_df[ur_df['Sentiment']=='Negative']
negative_ur_df


negative_ur_df.groupby('App')['Sentiment'].value_counts().nlargest(10).plot.barh(figsize=(15,8),color='crimson').invert_yaxis()
plt.title("Top 10 negative review apps")
plt.xlabel('Total number of negative reviews')
plt.legend()

<matplotlib.legend.Legend at 0x2eb4f6eca90>


merged_df.Sentiment_Subjectivity.value_counts()

0.000000    4134
1.000000    1653
0.500000    1579
0.600000    1133
0.750000    1095
            ... 
0.508052       1
0.454167       1
0.417316       1
0.765000       1
0.545714       1
Name: Sentiment_Subjectivity, Length: 4382, dtype: int64


plt.figure(figsize=(18,9))
plt.xlabel("Subjectivity")
plt.title("Distribution of Subjectivity")
plt.hist(merged_df[merged_df['Sentiment_Subjectivity'].notnull()]['Sentiment_Subjectivity'])
plt.show()


# scatterplot of sentiment polarity and sentiment subjectivity
plt.figure(figsize=(15, 10))
sns.scatterplot(ur_df['Sentiment_Subjectivity'], ur_df['Sentiment_Polarity'],
                hue = ur_df['Sentiment'], edgecolor='white', palette="inferno")
plt.title("Google Play Store Reviews Sentiment Analysis", fontsize=20)
plt.show()


paid_df['Content Rating'].value_counts().plot.bar(figsize=(10,10),color='c')
plt.legend()

<matplotlib.legend.Legend at 0x2eb5220e670>


free_df['Content Rating'].value_counts().plot.bar(figsize=(10,10),color='blue')
plt.legend()

<matplotlib.legend.Legend at 0x2eb50c18430>


print(ps_df['Last Updated'].head())
#fetch update year from date
ps_df["Update year"] = ps_df["Last Updated"].apply(lambda x: x.strftime('%Y')).astype('int64')

0   2018-01-07
1   2018-01-15
2   2018-08-01
3   2018-06-08
4   2018-06-20
Name: Last Updated, dtype: datetime64[ns]


fig, ax = plt.subplots(figsize=(12,6))
sns.regplot(x="Update year", y="Rating", data=ps_df)
plt.title("Update Year VS Rating")

Text(0.5, 1.0, 'Update Year VS Rating')


paid_df["Update year"] = paid_df["Last Updated"].apply(lambda x: x.strftime('%Y')).astype('int64') 
free_df["Update year"] = free_df["Last Updated"].apply(lambda x: x.strftime('%Y')).astype('int64')


paid_df.groupby("Update year")["App"].count().plot.line(marker='o')
free_df.groupby('Update year')['App'].count().plot.line(marker='o')

<AxesSubplot:xlabel='Update year'>


paid_df["Update month"] = paid_df["Last Updated"].apply(lambda x: x.strftime('%m')).astype('int64') 
free_df["Update month"] = free_df["Last Updated"].apply(lambda x: x.strftime('%m')).astype('int64')


paid_df.groupby("Update month")["App"].count().plot.bar(figsize=(10,8), color= "green")
plt.title("Paid Apps update over the month", size=20)
plt.legend()

<matplotlib.legend.Legend at 0x2eb4e8cf160>


free_df.groupby("Update month")["App"].count().plot.bar(figsize=(10,8), color='purple')
plt.title("Free Apps update over the month", size=20)
plt.legend()

<matplotlib.legend.Legend at 0x2eb47440730>

	Rating
count	9367.000000
mean	4.193338
std	0.537431
min	1.000000
25%	4.000000
50%	4.300000
75%	4.500000
max	19.000000

	Rating	Reviews	Size	Installs	Price
count	9649.000000	9.649000e+03	9649.000000	9.649000e+03	9649.000000
mean	4.192476	2.168145e+05	19.343659	7.785404e+06	1.100079
std	0.496528	1.832255e+06	20.589648	5.378557e+07	16.860857
min	1.000000	0.000000e+00	0.008300	0.000000e+00	0.000000
25%	4.000000	2.500000e+01	5.300000	1.000000e+03	0.000000
50%	4.300000	9.690000e+02	12.000000	1.000000e+05	0.000000
75%	4.500000	2.944500e+04	25.000000	1.000000e+06	0.000000
max	5.000000	7.815831e+07	100.000000	1.000000e+09	400.000000

	App	Translated_Review	Sentiment	Sentiment_Polarity	Sentiment_Subjectivity
1	10 Best Foods for You	This help eating healthy exercise regular basis	Positive	0.250000	0.288462
3	10 Best Foods for You	Works great especially going grocery store	Positive	0.400000	0.875000
4	10 Best Foods for You	Best idea us	Positive	1.000000	0.300000
5	10 Best Foods for You	Best way	Positive	1.000000	0.300000
6	10 Best Foods for You	Amazing	Positive	0.600000	0.900000
8	10 Best Foods for You	Looking forward app,	Neutral	0.000000	0.000000
9	10 Best Foods for You	It helpful site ! It help foods get !	Neutral	0.000000	0.000000
10	10 Best Foods for You	good you.	Positive	0.700000	0.600000
11	10 Best Foods for You	Useful information The amount spelling errors ...	Positive	0.200000	0.100000
12	10 Best Foods for You	Thank you! Great app!! Add arthritis, eyes, im...	Positive	0.750000	0.875000
13	10 Best Foods for You	Greatest ever Completely awesome maintain heal...	Positive	0.992188	0.866667
14	10 Best Foods for You	Good health...... Good health first priority.....	Positive	0.550000	0.511111
16	10 Best Foods for You	Health It's important world either life . thin...	Positive	0.450000	1.000000
17	10 Best Foods for You	Mrs sunita bhati I thankful developers,to make...	Positive	0.600000	0.666667
18	10 Best Foods for You	Very Useful in diabetes age 30. I need control...	Positive	0.295000	0.100000
19	10 Best Foods for You	One greatest apps.	Positive	1.000000	1.000000
20	10 Best Foods for You	good nice	Positive	0.650000	0.800000
21	10 Best Foods for You	Healthy Really helped	Positive	0.350000	0.350000
22	10 Best Foods for You	God health	Neutral	0.000000	0.000000
23	10 Best Foods for You	HEALTH SHOULD ALWAYS BE TOP PRIORITY. !!. ON M...	Positive	0.781250	0.500000
24	10 Best Foods for You	An excellent A useful	Positive	0.650000	0.500000

	Rating	Reviews	Size	Installs	Price
Rating	1.000000	0.050212	0.037378	0.034306	-0.018674
Reviews	0.050212	1.000000	0.066152	0.625158	-0.007603
Size	0.037378	0.066152	1.000000	0.030474	-0.019589
Installs	0.034306	0.625158	0.030474	1.000000	-0.009412
Price	-0.018674	-0.007603	-0.019589	-0.009412	1.000000

	Rating	Reviews	Size	Installs	Price	Sentiment_Polarity	Sentiment_Subjectivity
Rating	1.000000	0.075736	0.091094	0.020145	-0.010055	0.092903	0.068758
Reviews	0.075736	1.000000	0.190686	0.564256	-0.020591	-0.080021	-0.009315
Size	0.091094	0.190686	1.000000	0.040817	0.002484	-0.118398	0.013460
Installs	0.020145	0.564256	0.040817	1.000000	-0.025213	-0.057842	-0.006307
Price	-0.010055	-0.020591	0.002484	-0.025213	1.000000	0.024148	0.003182
Sentiment_Polarity	0.092903	-0.080021	-0.118398	-0.057842	0.024148	1.000000	0.259668
Sentiment_Subjectivity	0.068758	-0.009315	0.013460	-0.006307	0.003182	0.259668	1.000000

	App	Category	Rating	Reviews	Size	Installs	Type	Content Rating	Genres	Last Updated	Current Ver	Android Ver
0	Photo Editor & Candy Camera & Grid & ScrapBook	ART_AND_DESIGN	4.1	159	19M	10,000+	Free	Everyone	Art & Design	January 7, 2018	1.0.0	4.0.3 and up
1	Coloring book moana	ART_AND_DESIGN	3.9	967	14M	500,000+	Free	Everyone	Art & Design;Pretend Play	January 15, 2018	2.0.0	4.0.3 and up
2	U Launcher Lite – FREE Live Cool Themes, Hide ...	ART_AND_DESIGN	4.7	87510	8.7M	5,000,000+	Free	Everyone	Art & Design	August 1, 2018	1.2.4	4.0.3 and up
3	Sketch - Draw & Paint	ART_AND_DESIGN	4.5	215644	25M	50,000,000+	Free	Teen	Art & Design	June 8, 2018	Varies with device	4.2 and up
4	Pixel Draw - Number Art Coloring Book	ART_AND_DESIGN	4.3	967	2.8M	100,000+	Free	Everyone	Art & Design;Creativity	June 20, 2018	1.1	4.4 and up

	datatype	not null values	null value	% of the null value	unique count
App	object	10841	0	0.000000	9660
Category	object	10841	0	0.000000	34
Rating	float64	9367	1474	0.135965	40
Reviews	object	10841	0	0.000000	6002
Size	object	10841	0	0.000000	462
Installs	object	10841	0	0.000000	22
Type	object	10840	1	0.000092	3
Price	object	10841	0	0.000000	93
Content Rating	object	10840	1	0.000092	6
Genres	object	10841	0	0.000000	120
Last Updated	object	10841	0	0.000000	1378
Current Ver	object	10833	8	0.000738	2832
Android Ver	object	10838	3	0.000277	33

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Last Updated	Current Ver	Android Ver
4453	[substratum] Vacuum: P	PERSONALIZATION	4.4	230	11M	1,000+	Paid	$1.49	Everyone	Personalization	July 20, 2018	4.4	NaN
4490	Pi Dark [substratum]	PERSONALIZATION	4.5	189	2.1M	10,000+	Free	0	Everyone	Personalization	March 27, 2018	1.1	NaN
10472	Life Made WI-Fi Touchscreen Photo Frame	1.9	19.0	3.0M	1,000+	Free	0	Everyone	NaN	February 11, 2018	1.0.19	4.0 and up	NaN

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Last Updated	Current Ver	Android Ver
15	Learn To Draw Kawaii Characters	ART_AND_DESIGN	3.2	55	2.7M	5,000+	Free	0	Everyone	Art & Design	June 6, 2018	NaN	4.2 and up
1553	Market Update Helper	LIBRARIES_AND_DEMO	4.1	20145	11k	1,000,000+	Free	0	Everyone	Libraries & Demo	February 12, 2013	NaN	1.5 and up
6322	Virtual DJ Sound Mixer	TOOLS	4.2	4010	8.7M	500,000+	Free	0	Everyone	Tools	May 10, 2017	NaN	4.0 and up
6803	BT Master	FAMILY	NaN	0	222k	100+	Free	0	Everyone	Education	November 6, 2016	NaN	1.6 and up
7333	Dots puzzle	FAMILY	4.0	179	14M	50,000+	Paid	$0.99	Everyone	Puzzle	April 18, 2018	NaN	4.0 and up
7407	Calculate My IQ	FAMILY	NaN	44	7.2M	10,000+	Free	0	Everyone	Entertainment	April 3, 2017	NaN	2.3 and up
7730	UFO-CQ	TOOLS	NaN	1	237k	10+	Paid	$0.99	Everyone	Tools	July 4, 2016	NaN	2.0 and up
10342	La Fe de Jesus	BOOKS_AND_REFERENCE	NaN	8	658k	1,000+	Free	0	Everyone	Books & Reference	January 31, 2017	NaN	3.0 and up

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Last Updated	Current Ver	Android Ver
23	Mcqueen Coloring pages	ART_AND_DESIGN	NaN	61	7.0M	100,000+	Free	0	Everyone	Art & Design;Action & Adventure	March 7, 2018	1.0.0	4.1 and up
113	Wrinkles and rejuvenation	BEAUTY	NaN	182	5.7M	100,000+	Free	0	Everyone 10+	Beauty	September 20, 2017	8.0	3.0 and up
123	Manicure - nail design	BEAUTY	NaN	119	3.7M	50,000+	Free	0	Everyone	Beauty	July 23, 2018	1.3	4.1 and up
126	Skin Care and Natural Beauty	BEAUTY	NaN	654	7.4M	100,000+	Free	0	Teen	Beauty	July 17, 2018	1.15	4.1 and up
129	Secrets of beauty, youth and health	BEAUTY	NaN	77	2.9M	10,000+	Free	0	Mature 17+	Beauty	August 8, 2017	2.0	2.3 and up
...	...	...	...	...	...	...	...	...	...	...	...	...	...
10824	Cardio-FR	MEDICAL	NaN	67	82M	10,000+	Free	0	Everyone	Medical	July 31, 2018	2.2.2	4.4 and up
10825	Naruto & Boruto FR	SOCIAL	NaN	7	7.7M	100+	Free	0	Teen	Social	February 2, 2018	1.0	4.0 and up
10831	payermonstationnement.fr	MAPS_AND_NAVIGATION	NaN	38	9.8M	5,000+	Free	0	Everyone	Maps & Navigation	June 13, 2018	2.0.148.0	4.0 and up
10835	FR Forms	BUSINESS	NaN	0	9.6M	10+	Free	0	Everyone	Business	September 29, 2016	1.1.5	4.0 and up
10838	Parkinson Exercices FR	MEDICAL	NaN	3	9.5M	1,000+	Free	0	Everyone	Medical	January 20, 2017	1.0	2.2 and up

	App	Category	Rating	Reviews	Size	Installs	Type	Content Rating	Genres	Last Updated	Current Ver	Android Ver
1653	ROBLOX	GAME	4.5	4447388	67M	100,000,000+	Free	Everyone 10+	Adventure;Action & Adventure	July 31, 2018	2.347.225742	4.1 and up
1701	ROBLOX	GAME	4.5	4447346	67M	100,000,000+	Free	Everyone 10+	Adventure;Action & Adventure	July 31, 2018	2.347.225742	4.1 and up
1748	ROBLOX	GAME	4.5	4448791	67M	100,000,000+	Free	Everyone 10+	Adventure;Action & Adventure	July 31, 2018	2.347.225742	4.1 and up
1841	ROBLOX	GAME	4.5	4449882	67M	100,000,000+	Free	Everyone 10+	Adventure;Action & Adventure	July 31, 2018	2.347.225742	4.1 and up
1870	ROBLOX	GAME	4.5	4449910	67M	100,000,000+	Free	Everyone 10+	Adventure;Action & Adventure	July 31, 2018	2.347.225742	4.1 and up
2016	ROBLOX	FAMILY	4.5	4449910	67M	100,000,000+	Free	Everyone 10+	Adventure;Action & Adventure	July 31, 2018	2.347.225742	4.1 and up
2088	ROBLOX	FAMILY	4.5	4450855	67M	100,000,000+	Free	Everyone 10+	Adventure;Action & Adventure	July 31, 2018	2.347.225742	4.1 and up
2206	ROBLOX	FAMILY	4.5	4450890	67M	100,000,000+	Free	Everyone 10+	Adventure;Action & Adventure	July 31, 2018	2.347.225742	4.1 and up
4527	ROBLOX	FAMILY	4.5	4443407	67M	100,000,000+	Free	Everyone 10+	Adventure;Action & Adventure	July 31, 2018	2.347.225742	4.1 and up

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Last Updated	Current Ver	Android Ver
229	Quick PDF Scanner + OCR FREE	BUSINESS	4.2	80805	Varies with device	5,000,000+	Free	0	Everyone	Business	February 26, 2018	Varies with device	4.0.3 and up
236	Box	BUSINESS	4.2	159872	Varies with device	10,000,000+	Free	0	Everyone	Business	July 31, 2018	Varies with device	Varies with device
239	Google My Business	BUSINESS	4.4	70991	Varies with device	5,000,000+	Free	0	Everyone	Business	July 24, 2018	2.19.0.204537701	4.4 and up
256	ZOOM Cloud Meetings	BUSINESS	4.4	31614	37M	10,000,000+	Free	0	Everyone	Business	July 20, 2018	4.1.28165.0716	4.0 and up
261	join.me - Simple Meetings	BUSINESS	4.0	6989	Varies with device	1,000,000+	Free	0	Everyone	Business	July 16, 2018	4.3.0.508	4.4 and up
...	...	...	...	...	...	...	...	...	...	...	...	...	...
10715	FarmersOnly Dating	DATING	3.0	1145	1.4M	100,000+	Free	0	Mature 17+	Dating	February 25, 2016	2.2	4.0 and up
10720	Firefox Focus: The privacy browser	COMMUNICATION	4.4	36981	4.0M	1,000,000+	Free	0	Everyone	Communication	July 6, 2018	5.2	5.0 and up
10730	FP Notebook	MEDICAL	4.5	410	60M	50,000+	Free	0	Everyone	Medical	March 24, 2018	2.1.0.372	4.4 and up
10753	Slickdeals: Coupons & Shopping	SHOPPING	4.5	33599	12M	1,000,000+	Free	0	Everyone	Shopping	July 30, 2018	3.9	4.4 and up
10768	AAFP	MEDICAL	3.8	63	24M	10,000+	Free	0	Everyone	Medical	June 22, 2018	2.3.1	5.0 and up

	App	Category	Rating	Reviews	Size	Installs	Type	Price	Content Rating	Genres	Last Updated	Current Ver	Android Ver
234	TurboScan: scan documents and receipts in PDF	BUSINESS	4.7	11442	6.8M	100,000+	Paid	4.99	Everyone	Business	2018-03-25	1.5.2	4.0 and up
235	Tiny Scanner Pro: PDF Doc Scan	BUSINESS	4.8	10295	39M	100,000+	Paid	4.99	Everyone	Business	2017-04-11	3.4.6	3.0 and up
427	Puffin Browser Pro	COMMUNICATION	4.0	18247	Varies with device	100,000+	Paid	3.99	Everyone	Communication	2018-07-05	7.5.3.20547	4.1 and up
476	Moco+ - Chat, Meet People	DATING	4.2	1545	Varies with device	10,000+	Paid	3.99	Mature 17+	Dating	2018-06-19	2.6.139	4.1 and up
477	Calculator	DATING	2.6	57	6.2M	1,000+	Paid	6.99	Everyone	Dating	2017-10-25	1.1.6	4.0 and up
...	...	...	...	...	...	...	...	...	...	...	...	...	...
10735	FP VoiceBot	FAMILY	4.3	17	157k	100+	Paid	0.99	Mature 17+	Entertainment	2015-11-25	1.2	2.1 and up
10760	Fast Tract Diet	HEALTH_AND_FITNESS	4.4	35	2.4M	1,000+	Paid	7.99	Everyone	Health & Fitness	2018-08-08	1.9.3	4.2 and up
10782	Trine 2: Complete Story	GAME	3.8	252	11M	10,000+	Paid	16.99	Teen	Action	2015-02-27	2.22	5.0 and up
10785	sugar, sugar	FAMILY	4.2	1405	9.5M	10,000+	Paid	1.20	Everyone	Puzzle	2018-06-05	2.7	2.3 and up
10798	Word Search Tab 1 FR	FAMILY	4.3	0	1020k	50+	Paid	1.04	Everyone	Puzzle	2012-02-06	1.1	3.0 and up

	App	Category	Rating	Reviews	Size	Installs	Type	Content Rating	Genres	Last Updated	Current Ver	Android Ver
0	Photo Editor & Candy Camera & Grid & ScrapBook	ART_AND_DESIGN	4.1	159	19M	10000	Free	Everyone	Art & Design	2018-01-07	1.0.0	4.0.3 and up
1	Coloring book moana	ART_AND_DESIGN	3.9	967	14M	500000	Free	Everyone	Art & Design;Pretend Play	2018-01-15	2.0.0	4.0.3 and up
2	U Launcher Lite – FREE Live Cool Themes, Hide ...	ART_AND_DESIGN	4.7	87510	8.7M	5000000	Free	Everyone	Art & Design	2018-08-01	1.2.4	4.0.3 and up
3	Sketch - Draw & Paint	ART_AND_DESIGN	4.5	215644	25M	50000000	Free	Teen	Art & Design	2018-06-08	Varies with device	4.2 and up
4	Pixel Draw - Number Art Coloring Book	ART_AND_DESIGN	4.3	967	2.8M	100000	Free	Everyone	Art & Design;Creativity	2018-06-20	1.1	4.4 and up

	App	Translated_Review	Sentiment	Sentiment_Polarity	Sentiment_Subjectivity
0	10 Best Foods for You	I like eat delicious food. That's I'm cooking ...	Positive	1.00	0.533333
1	10 Best Foods for You	This help eating healthy exercise regular basis	Positive	0.25	0.288462
2	10 Best Foods for You	NaN	NaN	NaN	NaN
3	10 Best Foods for You	Works great especially going grocery store	Positive	0.40	0.875000
4	10 Best Foods for You	Best idea us	Positive	1.00	0.300000

	App	Translated_Review	Sentiment	Sentiment_Polarity	Sentiment_Subjectivity
32	10 Best Foods for You	No recipe book Unable recipe book.	Negative	-0.500000	0.500000
43	10 Best Foods for You	Waste time It needs internet time n ask calls ...	Negative	-0.200000	0.000000
68	10 Best Foods for You	Faltu plz waste ur time	Negative	-0.200000	0.000000
85	10 Best Foods for You	Crap Doesn't work	Negative	-0.800000	0.800000
95	10 Best Foods for You	Boring. I thought actually just texts that's i...	Negative	-0.325000	0.475000
...	...	...	...	...	...
64215	Housing-Real Estate & Property	Horrible app. I wanted list property get aroun...	Negative	-0.528571	0.717262
64216	Housing-Real Estate & Property	Worst app. We get nothing Time waste . They up...	Negative	-0.400000	0.250000
64220	Housing-Real Estate & Property	No response support team. After I login, unabl...	Negative	-0.377778	0.533333
64226	Housing-Real Estate & Property	Dumb app, I wanted post property rent give opt...	Negative	-0.287500	0.250000
64230	Housing-Real Estate & Property	Useless app, I searched flats kondapur, Hydera...	Negative	-0.316667	0.400000

	datatype	not null values	null value	% of the null value	unique count
App	object	64295	0	0.00	1074
Translated_Review	object	37427	26868	41.79	27994
Sentiment	object	37432	26863	41.78	3
Sentiment_Polarity	float64	37432	26863	41.78	5410
Sentiment_Subjectivity	float64	37432	26863	41.78	4474

	App	Translated_Review	Sentiment
268	11st	NaN	Neutral
15048	Birds Sounds Ringtones & Wallpapers	NaN	Neutral
22092	Calorie Counter - MyFitnessPal	NaN	Neutral
31623	DC Comics	NaN	Neutral
52500	Garden Photo Frames - Garden Photo Editor	NaN	Neutral

	data_type	count of non null values	unique_count
App	object	35929	816
Category	object	35929	33
Rating	float64	35929	22
Reviews	int32	35929	807
Size	float64	35929	166
Installs	int64	35929	12
Type	object	35929	2
Price	float64	35929	9
Content Rating	object	35929	5
Genres	object	35929	67
Last Updated	datetime64[ns]	35929	247
Current Ver	object	35929	498
Android Ver	object	35929	22
Translated_Review	object	35929	26682
Sentiment	object	35929	3
Sentiment_Polarity	float64	35929	5295
Sentiment_Subjectivity	float64	35929	4382

	App	Category	Rating	Reviews	Size	Installs	Type	Content Rating	Genres	Last Updated	Current Ver	Android Ver	Rating_group
152	Google Play Books	BOOKS_AND_REFERENCE	3.9	1433233	12.0	1000000000	Free	Teen	Books & Reference	2018-08-03	Varies with device	Varies with device	Above Average
335	Messenger – Text and Video Chat for Free	COMMUNICATION	4.0	56642847	12.0	1000000000	Free	Everyone	Communication	2018-08-01	Varies with device	Varies with device	Top rated
336	WhatsApp Messenger	COMMUNICATION	4.4	69119316	12.0	1000000000	Free	Everyone	Communication	2018-08-03	Varies with device	Varies with device	Top rated
338	Google Chrome: Fast & Secure	COMMUNICATION	4.3	9642995	12.0	1000000000	Free	Everyone	Communication	2018-08-01	Varies with device	Varies with device	Top rated
340	Gmail	COMMUNICATION	4.3	4604324	12.0	1000000000	Free	Everyone	Communication	2018-08-02	Varies with device	Varies with device	Top rated
341	Hangouts	COMMUNICATION	4.0	3419249	12.0	1000000000	Free	Everyone	Communication	2018-07-21	Varies with device	Varies with device	Top rated
391	Skype - free IM & video calls	COMMUNICATION	4.1	10484169	12.0	1000000000	Free	Everyone	Communication	2018-08-03	Varies with device	Varies with device	Top rated
865	Google Play Games	ENTERTAINMENT	4.3	7165362	12.0	1000000000	Free	Teen	Entertainment	2018-07-16	Varies with device	Varies with device	Top rated
1654	Subway Surfers	GAME	4.5	27722264	76.0	1000000000	Free	Everyone 10+	Arcade	2018-07-12	1.90.0	4.1 and up	Top rated
2544	Facebook	SOCIAL	4.1	78158306	12.0	1000000000	Free	Teen	Social	2018-08-03	Varies with device	Varies with device	Top rated

The Play Store apps data has enormous potential to drive app-making businesses to success. Actionable insights can be drawn for developers to work on and capture the Android market. ¶

Each app (row) has values for catergory, rating, size, and more. Another dataset contains customer reviews of the android apps.¶

Explore and analyze the data to discover key factors responsible for app engagement and success. ¶

📱 Hi everybody !¶

Problem Statements¶

What is Exploratory Data Analysis?¶

▶Exploring Play store data:¶

Lets Explore play store DataFrame¶

Cleaning of the data¶

Handling the NaN values in the Play store data¶

1). Android Ver: There are a total of 3 NaN values in this column.¶

2). Current Ver: There are a total of 8 NaN values in this column.¶

3). Type: There is only one NaN value in this column.¶

4). Rating: This column contains 1470 NaN values.¶

Handling duplicates values and Manipulating dataset:¶

1).Handling the duplicates in theApp column¶

2). Changing the datatype of the Last Updated column from string to datetime.¶

3). Changing the datatype of thePrice column from string to float.¶

4). Converting the values in theInstallscolumn from string datatype to integer datatype.¶

5). Converting the values in theSizecolumn to a same unit of measure(MB).¶

6). Converting the datatype of values in theReviewscolumn from string to int.¶

Data Exploration--Univariate & Bivariate Analysis¶

☘ Let us see what insight we can have on the basis of Size of an app¶

Size vs Rating¶

Exploring User_review dataframe¶

Handling the error and NaN values in the User reviews¶

Data Visualization on play store data:¶

1). Correlation Heatmap¶

Let us check if there is any co-relation in both the dataframes.¶

2). What is the ratio of number of Paid apps and Free apps?¶

3). Which category of Apps from the Content Rating column are found more on playstore ?¶

4).Top categories on Google Playstore?¶

5). Which category App's have most number of installs?¶

6). Average rating of the apps¶

7). What are the Top 10 installed apps in any category?¶

8). Top apps that are of free type.¶

9). Top apps that are of paid type.¶

10). Distribution of apps based on its size¶

11). Android version based on each category¶

Data Visualization on User Reviews:¶

1). Percentage of Review Sentiments¶

2). Apps with the highest number of positive reviews¶

3). Apps with the highest number of negative reviews.¶

4). Histogram of Subjectivity¶

5). Is sentiment_subjectivity proportional to sentiment_polarity?¶

How Content Rating affect over the App¶

1.) Paid App Content Rating¶

2.) Free App content Rating¶

3.) Does Last Update date has an effects on rating?¶

4.) Distribution of App update over the Year¶

5.) Distribution of Paid and Free app updated over the Month¶

▶Analysis Summary¶

Challenges & Future Work¶

`1). Android Ver: There are a total of 3 NaN values in this column.`¶

`2). Current Ver: There are a total of 8 NaN values in this column.`¶

`3). Type: There is only one NaN value in this column.`¶

`4). Rating: This column contains 1470 NaN values.`¶

`1).Handling the duplicates in the`App `column`¶

`2). Changing the datatype of the Last Updated column from string to datetime.`¶

`3). Changing the datatype of the`Price `column from string to float`.¶

`4). Converting the values in the`Installs`column from string datatype to integer datatype.`¶

`5). Converting the values in the`Size`column to a same unit of measure(MB).`¶

`6). Converting the datatype of values in the`Reviews`column from string to int.`¶

`Size vs Rating`¶

`1). Correlation Heatmap`¶

`2). What is the ratio of number of Paid apps and Free apps?`¶

`3). Which category of Apps from the Content Rating column are found more on playstore ?`¶

`4).Top categories on Google Playstore?`¶

`5). Which category App's have most number of installs?`¶

`6). Average rating of the apps`¶

`7). What are the Top 10 installed apps in any category?`¶

`8). Top apps that are of free type.`¶

`9). Top apps that are of paid type.`¶

`10). Distribution of apps based on its size`¶

`11). Android version based on each category`¶

`1). Percentage of Review Sentiments`¶

`2). Apps with the highest number of positive reviews`¶

`3). Apps with the highest number of negative reviews.`¶

`4). Histogram of Subjectivity`¶

`5). Is sentiment_subjectivity proportional to sentiment_polarity?`¶